For Katy

Articles that came out of our calls — things I said I’d look into or wasn’t sure about, checked against primary sources. Each ends with what was verified, when, and what stays inferred.

• Can a no-code Claude setup react to external events, or are scheduled tasks the ceiling?
• What do Claude’s permission modes actually gate, from always-ask to skip-everything?
• How fresh is a Google Drive doc when Claude reads it through the connector?
• What does the Claude desktop app do that claude.ai in the browser doesn’t?
• Why does AI search of Google Drive miss documents, and what fixes it?
• Where is Granola’s auto-join setting, and how does its privacy model compare to Fireflies?
• Where should standing context live — memory, project instructions, or files?
• Why do Slack reminders and bot messages arrive silently, and how do you make them notify?
• Can Claude chat or Cowork dispatch parallel subagents?
• Can AI fix a garbled meeting transcript, and can your tool learn your team’s vocabulary?